#
# -- Useful Reference Syntax --------------
#
# Some special characters are:
#
# abc  Letters
# 123    Digits
# \d      Any Digit
# \D      Any Non-digit character
# .       Any Character
# \.      Period
# [abc]   Only a, b, or c
# [^abc]  Not a, b, nor c
# [a-z]   Characters a to z
# [0-9]   Numbers 0 to 9
# \w      Any Alphanumeric character
# \W      Any Non-alphanumeric character
# {m}     m Repetitions
# {m,n}   m to n Repetitions
# *       Zero or more repetitions
# +       One or more repetitions
# ?       Optional character
# \s      Any Whitespace
# \S      Any Non-whitespace character
# ^...$     Starts and ends
# (...)     Capture Group
# (a(bc)) Capture Sub-group
# (.*)    Capture all
# (abc|def)   Matches abc or def

import re   # Python Module For Regular Expression

example_string="""\
suraj singh bisht\
SURAJ SINGH BISHT\
surajsinghbisht054@gmail.com\
www.bitforestinfo.com\
yashwantsinghbisht054@gmail.com\
0124-100-125-2563\
124-586-9875\
This is an example text\
"""
import re
# Meta Characters

# / Backslash
# ^ Caret
# $ Dollar Sign
# . Dot
# ? Question Mark
# * Asterisk
# | Pipe
# + Plus Sign
# ( Opening Parenthesis
# ) Closing Parenthesis
# [ Opening Square Bracket
# { The Opening Curly Brace

# Hmm, Now, You are wondering what are the usages of meta character.
# if i guess right then please try to rewind you memory and then you will find that
# many character from this list. we have already used in previous examples.
# For More Info Check my previous tutorials about regular expressions
#
# so, let's start this tutorial
#

#
# In this example we will use more useful functions.
# So, keep reading
#
# In this Techniques, We need to compile patterns. To do, we need to transforme patterns in bytecodes
# as shown in the below example

pattern = re.compile('suraj') # Here Compiling pattern in bytecodes

print pattern.match(example_string) # 

<_sre.SRE_Match object at 0x7f583c51b098>

# Here Our OUtput is <_sre.SRE_Match object at 0x7f583c65f578>
# its means we find match and if we got none in output then its mean no string matched found 
#
# Example 1.
#
pattern = re.compile('suraj|SURAJ') # Compiling

k=pattern.match(example_string) 

# Here, k.start()  Parameter For starting index number of matched keyword  and 
# for ending index number of matched keyword k.end() parameter  
print k.start(), k.end() 

# k.span() for retrive both starting index and ending index number both together
print k.span()

0 5
(0, 5)

#
# Example 2.
# 
example_string="""surajsinghbisht054@gmail.com www.bitforestinfo.com yashwantsinghbisht054@gmail.com 0124-100-125-2563 124-586-9875"""

pattern = re.compile('(\w+).(\d\d\d\d-\d\d\d-\d\d\d)')

result=pattern.search(example_string)

print result.group(0) # For all
print result.group(1) # 
print result.group(2) # 

com 0124-100-125
com
0124-100-125

#
# Example 3.
#
pattern.findall(example_string) # hmm, this function is already explained in previous tutorial

['suraj', 'SURAJ', 'suraj']

# let's Try some other examples
#
# Example 4.
# Here, I am Searching for Email addresses

example_string="""
suraj singh bisht
SURAJ SINGH BISHT
surajsinghbisht054@gmail.com
www.bitforestinfo.com
yashwantsinghbisht054@gmail.com
0124-100-125-2563
124-586-9875
This is an example text
"""

pattern = re.compile('([a-zA-Z0-9]+@[a-z]+.[a-z]+)') # Compiling

pattern.findall(example_string)

['surajsinghbisht054@gmail.com', 'yashwantsinghbisht054@gmail.com']

# Hmm, we got our result
# now, let's try to get result with its name.
# means here we will give name to pattern group
#
# Example 5.
#
# (?P<pattern_name>here_pattern)
pattern = re.compile('(?P<email>[a-zA-Z0-9]+@[a-z]+.[a-z]+)') # Comp

result=pattern.search(example_string)

result.groupdict()

{'email': 'surajsinghbisht054@gmail.com'}

# here, i am trying to search phone number
# Example 6.
#
pattern = re.compile('(?P<phone>\d{3}-\d{3}-\d{4})') # Comp

result=pattern.search(example_string)

result.groupdict()

{'phone': '100-125-2563'}

# Now, here we will try to search Email and number together
# Example 7.
#
pattern = re.compile('(?P<email>([a-zA-Z0-9]+@[a-z]+.[a-z]+))(\W.*\W.*\W)(?P<phone>\d{3}-\d{3}-\d{4})') # Comp

result=pattern.search(example_string)

if result:
    print result.groupdict()

{'phone': '124-586-9875', 'email': 'yashwantsinghbisht054@gmail.com'}

# Let's Try Some Simple Examples 
#
# Example 8.
#
patterns=['[a-zA-Z0-9]+@[a-z]+.[a-z]+',    # For Email
         '\d{3}-\d{3}-\d{4}',              # For Phone
         ]

for pattern in patterns:
    #print pattern,example_string
    result=re.search(pattern, example_string)
    if result:
        print result.start(),result.end()
        print example_string[result.start():result.end()]

surajsinghbisht054@gmail.com
100-125-2563

# In this Examples 
# We are trying to split string in small parts
# and our given pattern is the breaking point of line
# let's try this also
# Example 9.
#
re.split('sur.{2}', example_string) # Here, I want to break string from suraj keyword

['\n',
 ' singh bisht\nSURAJ SINGH BISHT\n',
 'singhbisht054@gmail.com\nwww.bitforestinfo.com\nyashwantsinghbisht054@gmail.com\n0124-100-125-2563\n124-586-9875\nThis is an example text\n']

# one more example
#
# Example 10.
#
example_string ="The is My Cat and This is my dog but this is my horse"
#
# let's try to break this line from "and" and "but" keyword
re.split('and|but', example_string)

['The is My Cat ', ' This is my dog ', ' this is my horse']

# Now, Move To Next Level and Discuss About Some Special Cases
#
# Python Provides Us with some flag that can help us to modify our search results
#
# Flags
# re.s, re.DOTALL 
# re.I, re.IGNORECASE
# re.L, re.LOCALE
# re.M, re.MULTILINE
# re.U, re.UNICODE
# re.X, re.VERBOSE

# For More Info Visit Here: https://docs.python.org/2/library/re.html#module-contents
#
# Example 11.
#
example_string="""
suraj singh bisht
SURAJ SINGH BISHT
surajsinghbisht054@gmail.com
www.bitforestinfo.com
yashwantsinghbisht054@gmail.com
0124-100-125-2563
124-586-9875
This is an example text
"""

print re.findall('SURAJ', example_string, re.IGNORECASE)
# as you can see In output, my input pattern is in uppercase but my output is in both lower and upper.

['suraj', 'SURAJ', 'suraj']

#
# Example 12.
#
print re.findall('BITF(.*)com', example_string, re.IGNORECASE| re.DOTALL)
#
# normally . character is for capturing all keyword except new line but because of re.DOTALL flag, now
# in this example . is also capturing new lines

['stinfo.blogspot.com\nyashwantsinghbisht054@']